Gokulnath2003
commited on
Commit
•
24f0334
1
Parent(s):
55dfcfe
Upload 4 files
Browse files- Perler-Text2Voice/.gitattributes +35 -0
- Perler-Text2Voice/README.md +14 -0
- Perler-Text2Voice/app.py +172 -0
- Perler-Text2Voice/requirements.txt +1 -0
Perler-Text2Voice/.gitattributes
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
Perler-Text2Voice/README.md
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Parler-TTS Mini
|
3 |
+
emoji: 🥖
|
4 |
+
colorFrom: blue
|
5 |
+
colorTo: pink
|
6 |
+
sdk: gradio
|
7 |
+
sdk_version: 4.26.0
|
8 |
+
app_file: app.py
|
9 |
+
pinned: false
|
10 |
+
license: apache-2.0
|
11 |
+
short_description: High-fidelity Text-To-Speech
|
12 |
+
---
|
13 |
+
|
14 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
Perler-Text2Voice/app.py
ADDED
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import spaces
|
2 |
+
import gradio as gr
|
3 |
+
import torch
|
4 |
+
from transformers.models.speecht5.number_normalizer import EnglishNumberNormalizer
|
5 |
+
from string import punctuation
|
6 |
+
import re
|
7 |
+
|
8 |
+
|
9 |
+
from parler_tts import ParlerTTSForConditionalGeneration
|
10 |
+
from transformers import AutoTokenizer, AutoFeatureExtractor, set_seed
|
11 |
+
|
12 |
+
device = "cuda:0" if torch.cuda.is_available() else "cpu"
|
13 |
+
|
14 |
+
|
15 |
+
repo_id = "parler-tts/parler_tts_mini_v0.1"
|
16 |
+
|
17 |
+
model = ParlerTTSForConditionalGeneration.from_pretrained(repo_id).to(device)
|
18 |
+
tokenizer = AutoTokenizer.from_pretrained(repo_id)
|
19 |
+
feature_extractor = AutoFeatureExtractor.from_pretrained(repo_id)
|
20 |
+
|
21 |
+
|
22 |
+
SAMPLE_RATE = feature_extractor.sampling_rate
|
23 |
+
SEED = 42
|
24 |
+
|
25 |
+
default_text = "Please surprise me and speak in whatever voice you enjoy."
|
26 |
+
examples = [
|
27 |
+
[
|
28 |
+
"Remember - this is only the first iteration of the model! To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data by a factor of five times.",
|
29 |
+
"A male speaker with a low-pitched voice delivering his words at a fast pace in a small, confined space with a very clear audio and an animated tone."
|
30 |
+
],
|
31 |
+
[
|
32 |
+
"'This is the best time of my life, Bartley,' she said happily.",
|
33 |
+
"A female speaker with a slightly low-pitched, quite monotone voice delivers her words at a slightly faster-than-average pace in a confined space with very clear audio.",
|
34 |
+
],
|
35 |
+
[
|
36 |
+
"Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
|
37 |
+
"A male speaker with a slightly high-pitched voice delivering his words at a slightly slow pace in a small, confined space with a touch of background noise and a quite monotone tone.",
|
38 |
+
],
|
39 |
+
[
|
40 |
+
"Montrose also, after having experienced still more variety of good and bad fortune, threw down his arms, and retired out of the kingdom.",
|
41 |
+
"A male speaker with a low-pitched voice delivers his words at a fast pace and an animated tone, in a very spacious environment, accompanied by noticeable background noise.",
|
42 |
+
],
|
43 |
+
]
|
44 |
+
|
45 |
+
number_normalizer = EnglishNumberNormalizer()
|
46 |
+
|
47 |
+
def preprocess(text):
|
48 |
+
text = number_normalizer(text).strip()
|
49 |
+
text = text.replace("-", " ")
|
50 |
+
if text[-1] not in punctuation:
|
51 |
+
text = f"{text}."
|
52 |
+
|
53 |
+
abbreviations_pattern = r'\b[A-Z][A-Z\.]+\b'
|
54 |
+
|
55 |
+
def separate_abb(chunk):
|
56 |
+
chunk = chunk.replace(".","")
|
57 |
+
print(chunk)
|
58 |
+
return " ".join(chunk)
|
59 |
+
|
60 |
+
abbreviations = re.findall(abbreviations_pattern, text)
|
61 |
+
for abv in abbreviations:
|
62 |
+
if abv in text:
|
63 |
+
text = text.replace(abv, separate_abb(abv))
|
64 |
+
return text
|
65 |
+
|
66 |
+
@spaces.GPU
|
67 |
+
def gen_tts(text, description):
|
68 |
+
inputs = tokenizer(description, return_tensors="pt").to(device)
|
69 |
+
prompt = tokenizer(preprocess(text), return_tensors="pt").to(device)
|
70 |
+
|
71 |
+
set_seed(SEED)
|
72 |
+
generation = model.generate(
|
73 |
+
input_ids=inputs.input_ids, prompt_input_ids=prompt.input_ids, do_sample=True, temperature=1.0
|
74 |
+
)
|
75 |
+
audio_arr = generation.cpu().numpy().squeeze()
|
76 |
+
|
77 |
+
return SAMPLE_RATE, audio_arr
|
78 |
+
|
79 |
+
|
80 |
+
css = """
|
81 |
+
#share-btn-container {
|
82 |
+
display: flex;
|
83 |
+
padding-left: 0.5rem !important;
|
84 |
+
padding-right: 0.5rem !important;
|
85 |
+
background-color: #000000;
|
86 |
+
justify-content: center;
|
87 |
+
align-items: center;
|
88 |
+
border-radius: 9999px !important;
|
89 |
+
width: 13rem;
|
90 |
+
margin-top: 10px;
|
91 |
+
margin-left: auto;
|
92 |
+
flex: unset !important;
|
93 |
+
}
|
94 |
+
#share-btn {
|
95 |
+
all: initial;
|
96 |
+
color: #ffffff;
|
97 |
+
font-weight: 600;
|
98 |
+
cursor: pointer;
|
99 |
+
font-family: 'IBM Plex Sans', sans-serif;
|
100 |
+
margin-left: 0.5rem !important;
|
101 |
+
padding-top: 0.25rem !important;
|
102 |
+
padding-bottom: 0.25rem !important;
|
103 |
+
right:0;
|
104 |
+
}
|
105 |
+
#share-btn * {
|
106 |
+
all: unset !important;
|
107 |
+
}
|
108 |
+
#share-btn-container div:nth-child(-n+2){
|
109 |
+
width: auto !important;
|
110 |
+
min-height: 0px !important;
|
111 |
+
}
|
112 |
+
#share-btn-container .wrap {
|
113 |
+
display: none !important;
|
114 |
+
}
|
115 |
+
"""
|
116 |
+
with gr.Blocks(css=css) as block:
|
117 |
+
gr.HTML(
|
118 |
+
"""
|
119 |
+
<div style="text-align: center; max-width: 700px; margin: 0 auto;">
|
120 |
+
<div
|
121 |
+
style="
|
122 |
+
display: inline-flex; align-items: center; gap: 0.8rem; font-size: 1.75rem;
|
123 |
+
"
|
124 |
+
>
|
125 |
+
<h1 style="font-weight: 900; margin-bottom: 7px; line-height: normal;">
|
126 |
+
Parler-TTS 🗣️
|
127 |
+
</h1>
|
128 |
+
</div>
|
129 |
+
</div>
|
130 |
+
"""
|
131 |
+
)
|
132 |
+
gr.HTML(
|
133 |
+
f"""
|
134 |
+
<p><a href="https://github.com/huggingface/parler-tts"> Parler-TTS</a> is a training and inference library for
|
135 |
+
high-fidelity text-to-speech (TTS) models. The model demonstrated here, <a href="https://huggingface.co/parler-tts/parler_tts_mini_v0.1"> Parler-TTS Mini v0.1</a>,
|
136 |
+
is the first iteration model trained using 10k hours of narrated audiobooks. It generates high-quality speech
|
137 |
+
with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).</p>
|
138 |
+
|
139 |
+
<p>Tips for ensuring good generation:
|
140 |
+
<ul>
|
141 |
+
<li>Include the term "very clear audio" to generate the highest quality audio, and "very noisy audio" for high levels of background noise</li>
|
142 |
+
<li>Punctuation can be used to control the prosody of the generations, e.g. use commas to add small breaks in speech</li>
|
143 |
+
<li>The remaining speech features (gender, speaking rate, pitch and reverberation) can be controlled directly through the prompt</li>
|
144 |
+
</ul>
|
145 |
+
</p>
|
146 |
+
"""
|
147 |
+
)
|
148 |
+
with gr.Row():
|
149 |
+
with gr.Column():
|
150 |
+
input_text = gr.Textbox(label="Input Text", lines=2, value=default_text, elem_id="input_text")
|
151 |
+
description = gr.Textbox(label="Description", lines=2, value="", elem_id="input_description")
|
152 |
+
run_button = gr.Button("Generate Audio", variant="primary")
|
153 |
+
with gr.Column():
|
154 |
+
audio_out = gr.Audio(label="Parler-TTS generation", type="numpy", elem_id="audio_out")
|
155 |
+
|
156 |
+
inputs = [input_text, description]
|
157 |
+
outputs = [audio_out]
|
158 |
+
gr.Examples(examples=examples, fn=gen_tts, inputs=inputs, outputs=outputs, cache_examples=True)
|
159 |
+
run_button.click(fn=gen_tts, inputs=inputs, outputs=outputs, queue=True)
|
160 |
+
gr.HTML(
|
161 |
+
"""
|
162 |
+
<p>To improve the prosody and naturalness of the speech further, we're scaling up the amount of training data to 50k hours of speech.
|
163 |
+
The v1 release of the model will be trained on this data, as well as inference optimisations, such as flash attention
|
164 |
+
and torch compile, that will improve the latency by 2-4x. If you want to find out more about how this model was trained and even fine-tune it yourself, check-out the
|
165 |
+
<a href="https://github.com/huggingface/parler-tts"> Parler-TTS</a> repository on GitHub.</p>
|
166 |
+
|
167 |
+
<p>The Parler-TTS codebase and its associated checkpoints are licensed under <a href='https://github.com/huggingface/parler-tts?tab=Apache-2.0-1-ov-file#readme'> Apache 2.0</a>.</p>
|
168 |
+
"""
|
169 |
+
)
|
170 |
+
|
171 |
+
block.queue()
|
172 |
+
block.launch(share=True)
|
Perler-Text2Voice/requirements.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
git+https://github.com/ylacombe/parler-tts.git@parler-tts-release
|